Automatic playlist continuation using a hybrid recommender system combining features from text and audio

TitleAutomatic playlist continuation using a hybrid recommender system combining features from text and audio
Publication TypeConference Paper
Year of Publication2018
Conference NameWorkshop on the RecSys Challenge 2018
AuthorsFerraro, A., Bogdanov D., Yoon J., Kim K. S., & Serra X.
ISBN Number978-1-4503-6586-4/18/10
AbstractThe ACM RecSys Challenge 2018 focuses on music recommendation in the context of automatic playlist continuation. In this paper, we describe our approach to the problem and the final hybrid system that was submitted to the challenge by our team Cocoplaya. This system consists in combining the recommendations produced by two different models using ranking fusion. The first model is based on Matrix Factorization and it incorporates information from tracks’ audio and playlist titles. The second model generates recommendations based on typical track co-occurrences considering their proximity in the playlists. The proposed approach is efficient and achieves a good overall performance, with our model ranked 4th on the creative track of the challenge leaderboard.
preprint/postprint documenthttps://arxiv.org/abs/1901.00450
Final publicationhttps://doi.org/10.1145/3267471.3267473
intranet